ai.intuitek.the-stall/the-stall

What we checked

Six static checks, weighted by risk. Every result reflects only what could be observed in the published package and repository — never intent.

• Injection surface

  fail25% of grade

  Tool descriptions/manifest scanned for instruction-injection patterns (imperatives at the model, hidden text, 'ignore previous', data-exfil URLs).

  tool "llm-proxy" param "prompt" description: text addressed to the model rather than describing a capability. tool "agent-access-check" param "url" description: off-vendor URL in a description (example.com); capability text should not name where data goes. tool "code-security-scan" param "repo_url" description: off-vendor URL in a description (github.com); capability text should not name where data goes. tool "company-research-bundle" param "website_url" description: off-vendor URL in a description (stripe.com); capability text should not name where data goes. tool "github-org-intel" param "org" description: off-vendor URL in a description (github.com); capability text should not name where data goes. tool "github-repo-intel" param "repo" description: off-vendor URL in a description (github.com); capability text should not name where data goes. tool "wayback-intel" param "url" description: off-vendor URL in a description (sec.gov); capability text should not name where data goes. tool "web-company-intel" param "url" description: off-vendor URL in a description (stripe.com); capability text should not name where data goes. tool "x402-endpoint-intel" param "target" description: off-vendor URL in a description (…); capability text should not name where data goes.

• Supply chain

  warn25% of grade

  Package provenance: namespace verification, repo linkage, maintainer count, account age, postinstall scripts, typosquat distance.

  no resolvable repository linked to the package (provenance unverifiable)

• Credential hygiene

  fail15% of grade

  How the server takes secrets (env vs plaintext config vs hardcoded); secrets appearing in tool schemas.

  tool "dex-swap-quote" has a secret-shaped input parameter "from_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "dex-swap-quote" has a secret-shaped input parameter "to_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "nft-metadata" has a secret-shaped input parameter "token_id" — secrets must never be tool parameters (the model would supply/handle the credential). tool "token-top-holders" has a secret-shaped input parameter "token_address" — secrets must never be tool parameters (the model would supply/handle the credential).

• Permission scope

  unscannable15% of grade

  Declared tools vs. breadth (filesystem, network, exec); flags shell-exec and unbounded filesystem access.

  No source files, package.json, or pyproject were fetched; cannot infer capability scope.

• Version behavior

  unscannable10% of grade

  Diff of tool definitions between versions; new permissions or changed descriptions in a patch release (the postmark-mcp class).

  no prior version to diff (first sight of ai.intuitek.the-stall/[email protected]); version-drift / rug-pull cannot be evaluated. Cold-start risk is covered by point-in-time checks (injection_surface, supply_chain, credential_hygiene), not here.

• Transport config

  fail10% of grade

  Remote servers: TLS and auth mode (none/token/OAuth). Local servers: whether the manifest indicates it phones home.

  remote MCP endpoint declares NO authentication (unauthenticated remote — nginx-ui/CVE-2026-33032 class)